The automatic generation of basic, factual questions from a single sentence of text is a problem in the field of natural language processing (NLP) that has received a considerable amount of attention in the past five years. Some studies have suggested splitting this problem into two parts: first, decomposing the source sentence into a set of smaller, simple sentences, and then transforming each...

This paper proposes a sentence selection method using a maximum entropy criterion to construct recording scripts for speech synthesis. In the conventional corpus design of speech synthesis, a greedy algorithm that maximizes phonetic coverage is often used. However, for statistical parametric speech synthesis, phonetic and prosodic contextual balance is important as well as the coverage. To take...

This paper describes a hierarchical neural network we propose for sentence classification to extract product information from product documents. The network classifies each sentence in a document into attribute and condition classes on the basis of word sequences and sentence sequences in the document. Experimental results showed the method using the proposed network significantly outperformed ...

Abstract Sentence matching is widely used in various natural language tasks, such as inference, paraphrase identification and question answering. For these we need to understand the logical semantic relationship between two sentences. Most current methods use all information within a sentence build model hence determine its another sentence. However, contained some sentences may cause redundanc...

The active imperative sentences often tend to sound harsh. sentence has a commanding meaning and ends with an exclamation mark. In the Indonesian language, be more polite, uses word politeness different structure. These polite are called passive sentences. Changing can done mathematically through several stages. stages determining set of word, types, using binary operations obtain rules for cha...

We have developed a question-answering system Metis with natural-language interface. Metis generates the answer to a question by comparing the semantic graph of the question sentence with sentences discovered on the Internet as knowledge source. Specifically, we first get a set of semantic frames for the question sentence, as the output from a semantic analysis system, SAGE. Then we extract sev...

Sentence compression is a task of creating a short grammatical sentence by removing extraneous words or phrases from an original sentence while preserving its meaning. Existing methods learn statistics on trimming context-free grammar (CFG) rules. However, these methods sometimes eliminate the original meaning by incorrectly removing important parts of sentences, because trimming probabilities ...

We propose a completely unsupervised method for mining parallel sentences from quasi-comparable bilingual texts which have very different sizes, and which include both in-topic and off-topic documents. We discuss and analyze different bilingual corpora with various levels of comparability. We propose that while better document matching leads to better parallel sentence extraction, better senten...